Command
Determines the original project intent from documentation and design artifacts, then compares it against the current implementation to identify discrepancies. Good output: a clear statement of intended behavior versus actual behavior, with specific gaps called out.
Command
Creates a new plugin with the proper directory structure, metadata files, and starter files. Good output: a complete, valid plugin skeleton that passes /validate-plugin immediately after creation.
Command
Ensures 90%+ test coverage, runs all tests with sub-agents, fixes failures, then creates a PR. This is a comprehensive test-and-ship workflow. Evals should run against a project that has tests, not the marketplace repo itself.
Command
Validates a plugin's directory structure, frontmatter fields, and content for consistency and correctness. Good output: a clear pass/fail result with specific findings for any structural or metadata issues.
Plugin Claude Code
BPMN 2.0 workflow tools: XML generation from natural language/markdown, and conversion to Draw.io format. Includes bundled bpmn2drawio Python tool.
Skill Claude CodeCodex
Generate BPMN 2.0 compliant XML files from natural language process descriptions OR from structured markdown business process documents. Use this skill when a user wants to create a BPMN workflow, convert a business process to BPMN XML, model a workflow diagram, or generate process definitions. Triggers on requests…
Skill Claude CodeCodex
Convert BPMN 2.0 XML files into Draw.io native format (.drawio) using the bpmn2drawio Python tool. Renders properly in Draw.io Desktop or web applications. Use this skill when a user wants to visualize a BPMN process in Draw.io, convert BPMN to editable diagrams, or create Draw.io files from process definitions.…
Plugin Claude Code
Personal Claude Code commands and skills for documentation review, architecture analysis, git workflows, document processing, and multi-source research.
Agent
Reviews data modeling, storage selection, lifecycle, access patterns, consistency, PII handling, and backup/recovery.
Agent
Reviews APIs, event streams, queues, webhooks, and third-party contracts for well-designed, resilient system boundaries.
Agent
Reviews structural performance and scalability risks — query performance, caching, concurrency, and capacity under worst-case load.
Agent
Operational-readiness review of CI/CD, IaC, deployment, config management, observability, runbooks, and resilience.
Agent
Reviews test strategy, pyramid distribution, coverage quality, CI gating, and test-environment fidelity.
Agent
Reviews regulatory posture, audit-trail completeness, control-framework mapping, data residency, vendor risk, and business continuity.
Agent
Threat-model-driven review of attack surface, authN/authZ, data protection, secrets, dependency vulnerabilities, and compliance controls.
Agent
Code-level review of quality, design patterns, technical debt, algorithm correctness, error handling, and testability.
Agent
Reviews architecture fit, design decisions, pattern selection, and NFR coverage — is the system designed to do what it needs at scale and able to evolve.
Agent
Fleet operations agent for the 5-machine homelab — SSH checks, scoped fixes, and mandatory LABNOTEBOOK logging.
Command
Meeting transcript to structured markdown report.
Command
Run a single domain agent from the architecture review team against a target codebase.
Command
Re-synthesize the executive summary from existing domain findings — use after editing findings, re-running a single agent, or resolving conflicts.
Command
Interactive Q&A session from questions JSON file.
Command
Document quality evaluation with scored assessment report.
Command
Automate version bumping across plugin files with CHANGELOG placeholder.